[dotenv@17.2.2] injecting env (8) from .env -- tip: ­ƒöÉ prevent committing .env to code: https://dotenvx.com/precommit
Ô£à leo-profanity initialis├® avec 2730 mots interdits (fr + en + custom)

­ƒÜÇ D├ëMARRAGE DES TESTS DE MOD├ëRATION
­ƒôà Date: 26/11/2025 23:35:01
­ƒöæ OpenAI API Key: Ô£à Pr├®sente


­ƒº¬ TESTS DE MOD├ëRATION AUTOMATIQUE OPENAI

============================================================

­ƒöì Test [SAFE] - Contenu normal - ├®chec scolaire
­ƒôØ Texte : "J'ai rat├® mon examen de maths, je suis vraiment d├®├ºu."
­ƒöì moderateText appel├® avec: J'ai rat├® mon examen de maths, je suis vraiment d├®├ºu.
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: false,
  categories: [],
  scores: {
    harassment: 0.0059770935447400215,
    'harassment/threatening': 0.000009461262661302227,
    sexual: 0.000026119031909571944,
    hate: 0.00007321812616608614,
    'hate/threatening': 0.0000010289513485400628,
    illicit: 0.00004173157606777201,
    'illicit/violent': 0.000003120191139396651,
    'self-harm/intent': 0.00026702520964274283,
    'self-harm/instructions': 0.000002212566909570261,
    'self-harm': 0.0005553218228658851,
    'sexual/minors': 0.00000640200641038395,
    violence: 0.000493111798506495,
    'violence/graphic': 0.0000021444948420913954
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.0059770935447400215, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.000009461262661302227, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=0.000026119031909571944, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.00007321812616608614, threshold=0.5
­ƒöì V├®rif hate/threatening: enabled=true, score=0.0000010289513485400628, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.00004173157606777201, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.000003120191139396651, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.00026702520964274283, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.000002212566909570261, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.0005553218228658851, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.00000640200641038395, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.000493111798506495, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.0000021444948420913954, threshold=undefined
­ƒôè R├®sultat final mod├®ration: { shouldBlock: false, triggeredCategories: [] }
Ô£à PASS - Flagg├®: false (attendu: false)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)

­ƒöì Test [SAFE] - Contenu normal - accident au travail
­ƒôØ Texte : "Mon premier jour au travail ne s'est pas bien pass├®, j'ai renvers├® du ..."
­ƒöì moderateText appel├® avec: Mon premier jour au travail ne s'est pas bien pass├®, j'ai renvers├® du caf├® sur mon patron.
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: false,
  categories: [],
  scores: {
    harassment: 0.02011794088077596,
    'harassment/threatening': 0.0030194784758956184,
    sexual: 0.00089952090870963,
    hate: 0.0012187999758924999,
    'hate/threatening': 0.000007368592981140821,
    illicit: 0.0037957375057486816,
    'illicit/violent': 0.000034062932773341,
    'self-harm/intent': 0.00021770169376519476,
    'self-harm/instructions': 0.0000017778551863194697,
    'self-harm': 0.0005379045088107247,
    'sexual/minors': 0.000024156629828672456,
    violence: 0.1236800283829491,
    'violence/graphic': 0.0015731933694596465
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.02011794088077596, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.0030194784758956184, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=0.00089952090870963, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.0012187999758924999, threshold=0.5
­ƒöì V├®rif hate/threatening: enabled=true, score=0.000007368592981140821, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.0037957375057486816, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.000034062932773341, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.00021770169376519476, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.0000017778551863194697, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.0005379045088107247, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.000024156629828672456, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.1236800283829491, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.0015731933694596465, threshold=undefined
­ƒôè R├®sultat final mod├®ration: { shouldBlock: false, triggeredCategories: [] }
Ô£à PASS - Flagg├®: false (attendu: false)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)

­ƒöì Test [SAFE] - Terme ethnique neutre - contexte ├®ducatif
­ƒôØ Texte : "Discussion dans une salle arabe sur l'architecture islamique"
­ƒöì moderateText appel├® avec: Discussion dans une salle arabe sur l'architecture islamique
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: false,
  categories: [],
  scores: {
    harassment: 0.005701666732975074,
    'harassment/threatening': 0.00004802972318863164,
    sexual: 0.00008559006367452268,
    hate: 0.007725937964817763,
    'hate/threatening': 0.000010720880092159908,
    illicit: 0.00003569706350376584,
    'illicit/violent': 0.00003799845147518645,
    'self-harm/intent': 0.0002219660831203052,
    'self-harm/instructions': 0.00021337902185586662,
    'self-harm': 0.00047624913019932136,
    'sexual/minors': 0.00000714190139989638,
    violence: 0.0005832949863420954,
    'violence/graphic': 0.000018235460794662427
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.005701666732975074, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.00004802972318863164, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=0.00008559006367452268, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.007725937964817763, threshold=0.5
­ƒöì V├®rif hate/threatening: enabled=true, score=0.000010720880092159908, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.00003569706350376584, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.00003799845147518645, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.0002219660831203052, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.00021337902185586662, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.00047624913019932136, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.00000714190139989638, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.0005832949863420954, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.000018235460794662427, threshold=undefined
­ƒôè R├®sultat final mod├®ration: { shouldBlock: false, triggeredCategories: [] }
Ô£à PASS - Flagg├®: false (attendu: false)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)

­ƒöì Test [SAFE] - Fait historique avec terme ethnique neutre
­ƒôØ Texte : "Les arabes ont invent├® l'alg├¿bre"
­ƒöì moderateText appel├® avec: Les arabes ont invent├® l'alg├¿bre
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: false,
  categories: [],
  scores: {
    harassment: 0.14066811249383807,
    'harassment/threatening': 0.000010071400221737608,
    sexual: 0.000009314593042575101,
    hate: 0.08715911994445524,
    'hate/threatening': 0.000008220189478350845,
    illicit: 0.000016219281637167375,
    'illicit/violent': 0.000002931153855960119,
    'self-harm/intent': 0.0000018631746484712008,
    'self-harm/instructions': 4.6378732973537256e-7,
    'self-harm': 0.00000297731143841062,
    'sexual/minors': 0.0000012219076020491008,
    violence: 0.000009170196905195049,
    'violence/graphic': 0.0000012606946239951315
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.14066811249383807, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.000010071400221737608, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=0.000009314593042575101, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.08715911994445524, threshold=0.5
­ƒöì V├®rif hate/threatening: enabled=true, score=0.000008220189478350845, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.000016219281637167375, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.000002931153855960119, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.0000018631746484712008, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=4.6378732973537256e-7, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.00000297731143841062, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.0000012219076020491008, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.000009170196905195049, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.0000012606946239951315, threshold=undefined
­ƒôè R├®sultat final mod├®ration: { shouldBlock: false, triggeredCategories: [] }
Ô£à PASS - Flagg├®: false (attendu: false)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)

­ƒöì Test [HATE] - Hate speech explicite - groupes ethniques
­ƒôØ Texte : "Je d├®teste les arabes et les noirs"
­ƒöì moderateText appel├® avec: Je d├®teste les arabes et les noirs
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: true,
  categories: [ 'harassment', 'hate' ],
  scores: {
    harassment: 0.976882250559417,
    'harassment/threatening': 0.001218427323031362,
    sexual: 0.00009850082967450695,
    hate: 0.9932453308860372,
    'hate/threatening': 0.003327131391257229,
    illicit: 0.00004442183589214344,
    'illicit/violent': 0.00000861465062380632,
    'self-harm/intent': 0.00021642339588120966,
    'self-harm/instructions': 0.000003944258675190877,
    'self-harm': 0.00047348232244292843,
    'sexual/minors': 0.00001488384825728813,
    violence: 0.0006069710175518718,
    'violence/graphic': 0.000016865275398914433
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.976882250559417, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.001218427323031362, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=0.00009850082967450695, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.9932453308860372, threshold=0.5
­ƒÜ½ Cat├®gorie hate d├®clench├®e !
­ƒöì V├®rif hate/threatening: enabled=true, score=0.003327131391257229, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.00004442183589214344, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.00000861465062380632, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.00021642339588120966, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.000003944258675190877, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.00047348232244292843, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.00001488384825728813, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.0006069710175518718, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.000016865275398914433, threshold=undefined
­ƒôè R├®sultat final mod├®ration: {
  shouldBlock: true,
  triggeredCategories: [ { category: 'hate', score: 0.9932453308860372, threshold: 0.5 } ]
}
Ô£à PASS - Flagg├®: true (attendu: true)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)
   ­ƒôè Cat├®gories: harassment, hate
   ­ƒÆ» Scores: hate: 99.3%, harassment: 97.7%

­ƒöì Test [HATE] - Insulte raciste - contexte injurieux
­ƒôØ Texte : "Sale arabe de merde"
­ƒöì moderateText appel├® avec: Sale arabe de merde
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: false,
  categories: [],
  scores: {
    harassment: 0.1996228729168001,
    'harassment/threatening': 0.0009475611050565076,
    sexual: 0.020751581986515787,
    hate: 0.10382095496206366,
    'hate/threatening': 0.00006166297347617125,
    illicit: 0.0037831260365793627,
    'illicit/violent': 0.00004044814978420809,
    'self-harm/intent': 0.00021217710837818755,
    'self-harm/instructions': 0.000005225226840386988,
    'self-harm': 0.000007484622751061123,
    'sexual/minors': 0.00006070755804415097,
    violence: 0.001165830836081277,
    'violence/graphic': 0.000033015272509780104
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.1996228729168001, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.0009475611050565076, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=0.020751581986515787, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.10382095496206366, threshold=0.5
­ƒöì V├®rif hate/threatening: enabled=true, score=0.00006166297347617125, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.0037831260365793627, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.00004044814978420809, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.00021217710837818755, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.000005225226840386988, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.000007484622751061123, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.00006070755804415097, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.001165830836081277, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.000033015272509780104, threshold=undefined
­ƒôè R├®sultat final mod├®ration: { shouldBlock: false, triggeredCategories: [] }
ÔØî FAIL - Flagg├®: false (attendu: true)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)

­ƒöì Test [HATE] - Slur raciste + message de haine
­ƒôØ Texte : "Les n├¿gres devraient retourner dans leur pays"
­ƒöì moderateText appel├® avec: Les n├¿gres devraient retourner dans leur pays
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: true,
  categories: [ 'harassment', 'harassment/threatening', 'hate' ],
  scores: {
    harassment: 0.8942349926807652,
    'harassment/threatening': 0.5540689128650629,
    sexual: 0.00012644219446392274,
    hate: 0.8803644004486374,
    'hate/threatening': 0.023797364851881518,
    illicit: 0.007561908424249326,
    'illicit/violent': 0.00008559006367452268,
    'self-harm/intent': 0.0002533919593552032,
    'self-harm/instructions': 0.00023615986099555835,
    'self-harm': 0.0004971468444439132,
    'sexual/minors': 0.00001442598644847886,
    violence: 0.022811203060018218,
    'violence/graphic': 0.000013135179706526775
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.8942349926807652, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.5540689128650629, threshold=0.5
­ƒÜ½ Cat├®gorie harassment/threatening d├®clench├®e !
­ƒöì V├®rif sexual: enabled=undefined, score=0.00012644219446392274, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.8803644004486374, threshold=0.5
­ƒÜ½ Cat├®gorie hate d├®clench├®e !
­ƒöì V├®rif hate/threatening: enabled=true, score=0.023797364851881518, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.007561908424249326, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.00008559006367452268, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.0002533919593552032, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.00023615986099555835, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.0004971468444439132, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.00001442598644847886, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.022811203060018218, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.000013135179706526775, threshold=undefined
­ƒôè R├®sultat final mod├®ration: {
  shouldBlock: true,
  triggeredCategories: [
    {
      category: 'harassment/threatening',
      score: 0.5540689128650629,
      threshold: 0.5
    },
    { category: 'hate', score: 0.8803644004486374, threshold: 0.5 }
  ]
}
Ô£à PASS - Flagg├®: true (attendu: true)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)
   ­ƒôè Cat├®gories: harassment, harassment/threatening, hate
   ­ƒÆ» Scores: harassment: 89.4%, hate: 88.0%, harassment/threatening: 55.4%

­ƒöì Test [HATE] - Slur anti-maghr├®bin
­ƒôØ Texte : "Bougnoule de merde"
­ƒöì moderateText appel├® avec: Bougnoule de merde
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: true,
  categories: [ 'harassment' ],
  scores: {
    harassment: 0.6514996780749901,
    'harassment/threatening': 0.0009398529545260549,
    sexual: 0.020347679031341454,
    hate: 0.035283664235328575,
    'hate/threatening': 0.000020342697805520655,
    illicit: 0.00003514382632807918,
    'illicit/violent': 0.000014653129390717958,
    'self-harm/intent': 0.0002139768867903779,
    'self-harm/instructions': 0.00021531444940491194,
    'self-harm': 0.0004571382759572523,
    'sexual/minors': 0.00003353501304664781,
    violence: 0.016003914400400904,
    'violence/graphic': 0.000050333557545281144
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.6514996780749901, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.0009398529545260549, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=0.020347679031341454, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.035283664235328575, threshold=0.5
­ƒöì V├®rif hate/threatening: enabled=true, score=0.000020342697805520655, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.00003514382632807918, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.000014653129390717958, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.0002139768867903779, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.00021531444940491194, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.0004571382759572523, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.00003353501304664781, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.016003914400400904, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.000050333557545281144, threshold=undefined
­ƒôè R├®sultat final mod├®ration: { shouldBlock: false, triggeredCategories: [] }
ÔØî FAIL - Flagg├®: false (attendu: true)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)

­ƒöì Test [HATE] - Slur antis├®mite
­ƒôØ Texte : "Sale youpin"
­ƒöì moderateText appel├® avec: Sale youpin
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: false,
  categories: [],
  scores: {
    harassment: 0.00003799845147518645,
    'harassment/threatening': 0.000014202364022997911,
    sexual: 0.0029863021744691264,
    hate: 0.000010391067562761452,
    'hate/threatening': 8.939696304799168e-7,
    illicit: 0.0053011322000834195,
    'illicit/violent': 0.000016603846953733614,
    'self-harm/intent': 0.0000036478537675800286,
    'self-harm/instructions': 0.000005391084403253366,
    'self-harm': 0.000008682210299865954,
    'sexual/minors': 0.000038596609058077356,
    violence: 0.0005360157526065469,
    'violence/graphic': 0.000009028039015031105
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.00003799845147518645, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.000014202364022997911, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=0.0029863021744691264, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.000010391067562761452, threshold=0.5
­ƒöì V├®rif hate/threatening: enabled=true, score=8.939696304799168e-7, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.0053011322000834195, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.000016603846953733614, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.0000036478537675800286, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.000005391084403253366, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.000008682210299865954, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.000038596609058077356, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.0005360157526065469, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.000009028039015031105, threshold=undefined
­ƒôè R├®sultat final mod├®ration: { shouldBlock: false, triggeredCategories: [] }
ÔØî FAIL - Flagg├®: false (attendu: true)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)

­ƒöì Test [HATE] - Hate speech anglais
­ƒôØ Texte : "I hate niggers and jews"
­ƒöì moderateText appel├® avec: I hate niggers and jews
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: true,
  categories: [ 'harassment', 'hate' ],
  scores: {
    harassment: 0.9637303401534284,
    'harassment/threatening': 0.0063491065882896915,
    sexual: 0.00008295891883591029,
    hate: 0.8818232672526001,
    'hate/threatening': 0.003483489981590025,
    illicit: 0.00003175087886569813,
    'illicit/violent': 0.000009915273115920183,
    'self-harm/intent': 0.0002142503208503807,
    'self-harm/instructions': 0.000004198630823683514,
    'self-harm': 0.0004552008131639649,
    'sexual/minors': 0.000007602479448313689,
    violence: 0.0012885036886187368,
    'violence/graphic': 0.000017400543552708932
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.9637303401534284, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.0063491065882896915, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=0.00008295891883591029, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.8818232672526001, threshold=0.5
­ƒÜ½ Cat├®gorie hate d├®clench├®e !
­ƒöì V├®rif hate/threatening: enabled=true, score=0.003483489981590025, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.00003175087886569813, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.000009915273115920183, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.0002142503208503807, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.000004198630823683514, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.0004552008131639649, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.000007602479448313689, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.0012885036886187368, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.000017400543552708932, threshold=undefined
­ƒôè R├®sultat final mod├®ration: {
  shouldBlock: true,
  triggeredCategories: [ { category: 'hate', score: 0.8818232672526001, threshold: 0.5 } ]
}
Ô£à PASS - Flagg├®: true (attendu: true)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)
   ­ƒôè Cat├®gories: harassment, hate
   ­ƒÆ» Scores: harassment: 96.4%, hate: 88.2%

­ƒöì Test [VIOLENCE] - Menace de violence physique
­ƒôØ Texte : "Je vais te casser la figure si tu continues"
­ƒöì moderateText appel├® avec: Je vais te casser la figure si tu continues
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: true,
  categories: [ 'harassment', 'harassment/threatening', 'violence' ],
  scores: {
    harassment: 0.653992672469446,
    'harassment/threatening': 0.5492578293645041,
    sexual: 0.0029970979054966492,
    hate: 0.007304509695555215,
    'hate/threatening': 0.00009110511944006454,
    illicit: 0.020351806557553028,
    'illicit/violent': 0.0020556458560793277,
    'self-harm/intent': 0.00030858533984205353,
    'self-harm/instructions': 0.00022659152631606457,
    'self-harm': 0.004668255196716094,
    'sexual/minors': 0.000014653129390717958,
    violence: 0.9433518738468445,
    'violence/graphic': 0.0015974764130775882
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.653992672469446, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.5492578293645041, threshold=0.5
­ƒÜ½ Cat├®gorie harassment/threatening d├®clench├®e !
­ƒöì V├®rif sexual: enabled=undefined, score=0.0029970979054966492, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.007304509695555215, threshold=0.5
­ƒöì V├®rif hate/threatening: enabled=true, score=0.00009110511944006454, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.020351806557553028, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.0020556458560793277, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.00030858533984205353, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.00022659152631606457, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.004668255196716094, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.000014653129390717958, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.9433518738468445, threshold=0.6
­ƒÜ½ Cat├®gorie violence d├®clench├®e !
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.0015974764130775882, threshold=undefined
­ƒôè R├®sultat final mod├®ration: {
  shouldBlock: true,
  triggeredCategories: [
    {
      category: 'harassment/threatening',
      score: 0.5492578293645041,
      threshold: 0.5
    },
    { category: 'violence', score: 0.9433518738468445, threshold: 0.6 }
  ]
}
Ô£à PASS - Flagg├®: true (attendu: true)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)
   ­ƒôè Cat├®gories: harassment, harassment/threatening, violence
   ­ƒÆ» Scores: violence: 94.3%, harassment: 65.4%, harassment/threatening: 54.9%

­ƒöì Test [VIOLENCE] - Menace de meurtre
­ƒôØ Texte : "Je vais tuer mon voisin"
­ƒöì moderateText appel├® avec: Je vais tuer mon voisin
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: true,
  categories: [ 'harassment', 'harassment/threatening', 'violence' ],
  scores: {
    harassment: 0.568969485636238,
    'harassment/threatening': 0.5259965560860783,
    sexual: 0.00005193048644949271,
    hate: 0.013373319633101465,
    'hate/threatening': 0.004551077322881235,
    illicit: 0.20486139471966555,
    'illicit/violent': 0.0924340381051842,
    'self-harm/intent': 0.00032415278557820575,
    'self-harm/instructions': 0.00021428634147831863,
    'self-harm': 0.0005497288249495183,
    'sexual/minors': 0.0000020785170435063726,
    violence: 0.9530116037099625,
    'violence/graphic': 0.00003150386940813393
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.568969485636238, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.5259965560860783, threshold=0.5
­ƒÜ½ Cat├®gorie harassment/threatening d├®clench├®e !
­ƒöì V├®rif sexual: enabled=undefined, score=0.00005193048644949271, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.013373319633101465, threshold=0.5
­ƒöì V├®rif hate/threatening: enabled=true, score=0.004551077322881235, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.20486139471966555, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.0924340381051842, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.00032415278557820575, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.00021428634147831863, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.0005497288249495183, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.0000020785170435063726, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.9530116037099625, threshold=0.6
­ƒÜ½ Cat├®gorie violence d├®clench├®e !
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.00003150386940813393, threshold=undefined
­ƒôè R├®sultat final mod├®ration: {
  shouldBlock: true,
  triggeredCategories: [
    {
      category: 'harassment/threatening',
      score: 0.5259965560860783,
      threshold: 0.5
    },
    { category: 'violence', score: 0.9530116037099625, threshold: 0.6 }
  ]
}
Ô£à PASS - Flagg├®: true (attendu: true)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)
   ­ƒôè Cat├®gories: harassment, harassment/threatening, violence
   ­ƒÆ» Scores: violence: 95.3%, harassment: 56.9%, harassment/threatening: 52.6%

­ƒöì Test [SEXUAL] - Contenu sexuel explicite
­ƒôØ Texte : "I want to have sex with you right now, you're so hot"
­ƒöì moderateText appel├® avec: I want to have sex with you right now, you're so hot
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: true,
  categories: [ 'sexual' ],
  scores: {
    harassment: 0.005613482909443095,
    'harassment/threatening': 0.000747540544174614,
    sexual: 0.9222062635446245,
    hate: 0.000016603846953733614,
    'hate/threatening': 0.0000014738981974494932,
    illicit: 0.000009610241549947397,
    'illicit/violent': 0.000005920916517463734,
    'self-harm/intent': 0.00021320602528870992,
    'self-harm/instructions': 0.0000013420013504783412,
    'self-harm': 0.000012339457598623173,
    'sexual/minors': 0.00015011822567369918,
    violence: 0.0005323933551511255,
    'violence/graphic': 0.0000015689549727726036
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.005613482909443095, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.000747540544174614, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=0.9222062635446245, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.000016603846953733614, threshold=0.5
­ƒöì V├®rif hate/threatening: enabled=true, score=0.0000014738981974494932, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.000009610241549947397, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.000005920916517463734, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.00021320602528870992, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.0000013420013504783412, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.000012339457598623173, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.00015011822567369918, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.0005323933551511255, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.0000015689549727726036, threshold=undefined
­ƒôè R├®sultat final mod├®ration: { shouldBlock: false, triggeredCategories: [] }
ÔØî FAIL - Flagg├®: false (attendu: true)
   ­ƒñû Source: OpenAI API (omni-moderation-latest)

============================================================

­ƒôè R├ëSULTATS FINAUX : 9/13 tests r├®ussis
ÔÜá´©Å  4 test(s) ├®chou├®(s). D├®tails ci-dessus.


­ƒÄ» TEST MOD├ëRATION DE FAILS COMPLETS

============================================================

­ƒôØ Fail normal (doit passer)
   Titre: "Mon premier jour catastrophique au travail"
   Description: "J'ai renvers├® du caf├® sur mon patron lors de ma premi├¿re r├®u..."
­ƒöì moderateText appel├® avec: Mon premier jour catastrophique au travail
J'ai renvers├® du caf├® sur mon patron lors de ma premi├¿re 
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: false,
  categories: [],
  scores: {
    harassment: 0.01950886793918398,
    'harassment/threatening': 0.0009398529545260549,
    sexual: 0.00007437028637763686,
    hate: 0.00009850082967450695,
    'hate/threatening': 0.000002212566909570261,
    illicit: 0.00004044814978420809,
    'illicit/violent': 0.000015843621910252592,
    'self-harm/intent': 0.000005225226840386988,
    'self-harm/instructions': 6.339210403977636e-7,
    'self-harm': 0.0004753051800293774,
    'sexual/minors': 0.000007967300986103147,
    violence: 0.07110434318346032,
    'violence/graphic': 0.000048785712278226595
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.01950886793918398, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.0009398529545260549, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=0.00007437028637763686, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.00009850082967450695, threshold=0.5
­ƒöì V├®rif hate/threatening: enabled=true, score=0.000002212566909570261, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.00004044814978420809, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.000015843621910252592, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.000005225226840386988, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=6.339210403977636e-7, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.0004753051800293774, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.000007967300986103147, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.07110434318346032, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.000048785712278226595, threshold=undefined
­ƒôè R├®sultat final mod├®ration: { shouldBlock: false, triggeredCategories: [] }
Ô£à PASS R├®sultat: AUTORIS├ë Ô£à (attendu: AUTORIS├ë)

­ƒôØ Hate speech (doit ├¬tre bloqu├®)
   Titre: "Test hate speech"
   Description: "Je d├®teste les arabes et les juifs..."
­ƒöì moderateText appel├® avec: Test hate speech
Je d├®teste les arabes et les juifs
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: true,
  categories: [ 'harassment', 'hate' ],
  scores: {
    harassment: 0.8420464786833548,
    'harassment/threatening': 0.003002969819479634,
    sexual: 0.00002453694805426225,
    hate: 0.8287414305123032,
    'hate/threatening': 0.004214662807098416,
    illicit: 0.005296141712652269,
    'illicit/violent': 0.000021318756129065198,
    'self-harm/intent': 0.00021659756423044233,
    'self-harm/instructions': 0.0002123029091656883,
    'self-harm': 0.0004558265687732626,
    'sexual/minors': 0.00000498595821272702,
    violence: 0.0011978401309281443,
    'violence/graphic': 0.000013342001090985438
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.8420464786833548, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=0.003002969819479634, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=0.00002453694805426225, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.8287414305123032, threshold=0.5
­ƒÜ½ Cat├®gorie hate d├®clench├®e !
­ƒöì V├®rif hate/threatening: enabled=true, score=0.004214662807098416, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=0.005296141712652269, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=0.000021318756129065198, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=0.00021659756423044233, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=0.0002123029091656883, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=0.0004558265687732626, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=0.00000498595821272702, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=0.0011978401309281443, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=0.000013342001090985438, threshold=undefined
­ƒôè R├®sultat final mod├®ration: {
  shouldBlock: true,
  triggeredCategories: [ { category: 'hate', score: 0.8287414305123032, threshold: 0.5 } ]
}
Ô£à PASS R├®sultat: BLOQU├ë ÔØî (attendu: BLOQU├ë)
   ­ƒôè Cat├®gories: harassment, hate
­ƒÜ¿ Fail flagg├® par mod├®ration: {
  title: 'Test hate speech',
  categories: {
    harassment: true,
    'harassment/threatening': false,
    sexual: false,
    hate: true,
    'hate/threatening': false,
    illicit: false,
    'illicit/violent': false,
    'self-harm/intent': false,
    'self-harm/instructions': false,
    'self-harm': false,
    'sexual/minors': false,
    violence: false,
    'violence/graphic': false
  }
}

­ƒôØ Terme ethnique neutre (doit passer)
   Titre: "Discussion culturelle"
   Description: "Les arabes ont contribu├® ├á l'astronomie et aux math├®matiques..."
­ƒöì moderateText appel├® avec: Discussion culturelle
Les arabes ont contribu├® ├á l'astronomie et aux math├®matiques
­ƒöæ API Key pr├®sente: true longueur: 164
­ƒôñ Envoi requ├¬te ├á OpenAI Moderation API (omni-moderation-latest)...
Ô£à R├®ponse OpenAI re├ºue: {
  flagged: false,
  categories: [],
  scores: {
    harassment: 0.0006975119688781332,
    'harassment/threatening': 6.339210403977636e-7,
    sexual: 8.664653147910923e-7,
    hate: 0.00004238847419937498,
    'hate/threatening': 2.994440981371515e-7,
    illicit: 8.664653147910923e-7,
    'illicit/violent': 3.84493505874534e-7,
    'self-harm/intent': 5.014734822853044e-7,
    'self-harm/instructions': 7.338209805254082e-8,
    'self-harm': 5.093705003229987e-7,
    'sexual/minors': 1.5057017254045334e-7,
    violence: 4.78509449489012e-7,
    'violence/graphic': 2.2603242979035749e-7
  }
}
ÔØî Erreur SQL: La table 'faildaily.moderation_settings' n'existe pas
­ƒôØ Requ├¬te: SELECT category, enabled, severity_threshold FROM moderation_settings
­ƒôï Param├¿tres: []
ÔØî Erreur chargement config mod├®ration: La table 'faildaily.moderation_settings' n'existe pas
ÔÜÖ´©Å Settings de mod├®ration: {
  hate: { enabled: true, threshold: 0.5 },
  'hate/threatening': { enabled: true, threshold: 0.5 },
  'harassment/threatening': { enabled: true, threshold: 0.5 },
  'self-harm/intent': { enabled: true, threshold: 0.5 },
  'sexual/minors': { enabled: true, threshold: 0.01 },
  violence: { enabled: true, threshold: 0.6 }
}
­ƒöì V├®rif harassment: enabled=undefined, score=0.0006975119688781332, threshold=undefined
­ƒöì V├®rif harassment/threatening: enabled=true, score=6.339210403977636e-7, threshold=0.5
­ƒöì V├®rif sexual: enabled=undefined, score=8.664653147910923e-7, threshold=undefined
­ƒöì V├®rif hate: enabled=true, score=0.00004238847419937498, threshold=0.5
­ƒöì V├®rif hate/threatening: enabled=true, score=2.994440981371515e-7, threshold=0.5
­ƒöì V├®rif illicit: enabled=undefined, score=8.664653147910923e-7, threshold=undefined
­ƒöì V├®rif illicit/violent: enabled=undefined, score=3.84493505874534e-7, threshold=undefined
­ƒöì V├®rif self-harm/intent: enabled=true, score=5.014734822853044e-7, threshold=0.5
­ƒöì V├®rif self-harm/instructions: enabled=undefined, score=7.338209805254082e-8, threshold=undefined
­ƒöì V├®rif self-harm: enabled=undefined, score=5.093705003229987e-7, threshold=undefined
­ƒöì V├®rif sexual/minors: enabled=true, score=1.5057017254045334e-7, threshold=0.01
­ƒöì V├®rif violence: enabled=true, score=4.78509449489012e-7, threshold=0.6
­ƒöì V├®rif violence/graphic: enabled=undefined, score=2.2603242979035749e-7, threshold=undefined
­ƒôè R├®sultat final mod├®ration: { shouldBlock: false, triggeredCategories: [] }
Ô£à PASS R├®sultat: AUTORIS├ë Ô£à (attendu: AUTORIS├ë)

============================================================

­ƒôè R├ëSULTATS FAILS : 3/3 tests r├®ussis


============================================================
­ƒôê RAPPORT FINAL
============================================================
Ô£à Tests r├®ussis: 12/16 (75.0%)
   - Tests texte: 9/13
   - Tests fails: 3/3

ÔÜá´©Å  4 test(s) ├®chou├®(s)
­ƒôï V├®rifier les logs ci-dessus pour les d├®tails